© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11623
    Prev
    Next
    INDEX
    Explanations

    741741

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on odd subword fragments and formatting artifacts (e.g. pieces broken by soft-hyphens, stray punctuation, bracketed slices, or other non-standard characters).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    젹
    0.38
    룔
    0.35
    __|
    0.34
     및
    0.34
    <unused314>
    0.34
     বেশী
    0.33
     Noch
    0.33
     мүмк
    0.32
    <unused640>
    0.32
    깆
    0.31
    POSITIVE LOGITS
    АС
    0.29
    đe
    0.29
    Some
    0.28
    ллер
    0.28
    мп
    0.27
     عندما
    0.27
    oudre
    0.27
    Cuando
    0.27
    Ꭷ
    0.27
    َه
    0.27
    Activations Density 0.048%

    No Known Activations